Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| SanctionsKit developer MCP sanctionskit/sanctions-kit-mcp-plugin Sanctions API docs and request validation, with account-linked synthetic sandbox testing. | |
| SanctumAI — Credential Vault for AI Agents sanctumsec/sanctum Credential vault for AI agents — encrypted storage, lease-based access, CRP support. | |
| SandBase Harness sandbaseai/sandbase-harness Stdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation. | |
| SlateHut sandeep1995/form2web AI website builder (Wix/Framer alt). SlateHut MCP over HTTP: tools, schemas. Bearer auth. | |
| io.github.sandeepbazar/ocm-mcp-server sandeepbazar/ocm-mcp-server Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit. | |
| Marketing Skills Directory sandeepkelvadi/mkt-skills Search, browse & read 340+ Claude Code marketing & SEO skills from any MCP client. | |
| Brownfield Cartographer sanoy24/the-brownfield-cartographer Local impact and table, column and Airflow lineage for SQL, dbt, Python and TypeScript repos. | |
| Panya — peptide vendor matchmaker santorareplica/panya-platform Peptide vendor matchmaker. 11-signal rubric, GLP-1 + 25 peptides, region-aware, free. | |
| TinyScale sanv725/tinyscale-agent Add waitlists, feedback widgets, changelogs and deploy checks to a SaaS app; claim with no card. | |
| Obolus sanzation/obolus-finance-api Read-only payroll calculations and multi-country tax comparisons for eight countries. | |
| SAP HANA CLI sap-samples/hana-developer-cli-tool-example 150+ SAP HANA database tools as MCP tools for AI assistants | |
| io.github.SAP/fiori-mcp-server sap/open-ux-tools SAP Fiori - Model Context Protocol (MCP) server | |
| Free the Tools sapience-design/freethetools Local PDF, image, data and text tools for AI assistants. Files stay on your computer. | |
| AIppocampus sapientropic/aippocampus Local-first, source-backed continuity for AI agents via stdio MCP. | |
| io.github.sapientsai/microsoft365-mcp-server sapientsai/microsoft365-mcp-server Microsoft 365 via Graph — mail, calendar, contacts, files, Teams, Planner, OneNote, To Do. | |
| io.github.sapientsai/patents-mcp-server sapientsai/patents-mcp-server Patent intelligence — USPTO Open Data, PTAB, EPO OPS and BigQuery full-text search. | |
| io.github.sapiom/mcp sapiom/sapiom-js Local Sapiom developer MCP for authoring, testing, deploying, and inspecting agents. | |
| Folkso saplq/folkso-plugin Find real people for a task right in ChatGPT and Claude. Everyone chose to appear in AI answers. | |
| AI Divination Skills sapuyou45-bit/ai-divination-skills Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results. | |
| Afromorphism sarabalawson/website Read-only access to S. Araba Lawson's Afromorphism essays, glossary, books, and site. | |
| PaperPorter sarchak/paperporter-plugins Fill official PDF forms, like city permits and business licenses, in their original layout. | |
| io.github.sarduine13-star/agent-teller sarduine13-star/botguard-agent Verify AI agent payments and detect fraud. Input: agent_id, amount, service_id. | |
| Draw me saritas57/drawme Public art experiment: draw Mehmet Sarıtaş as SVG, submit it, see the wall, vote for drawings. | |
| Campfyrr sarkars/campfyrr Campfyrr, shared team memory for Claude Code | |
| paidfor sarmadahsan/paidfor-index Check an x402 seller before paying: verdict, failure rate and evidence from paid calls on Base. | |
| Agent Discovery Board by SarnAI sarnai-dev/agent-discovery-board-public Free directory of MCP servers and x402 APIs for AI agents. Find them, or list your own in one call. | |
| Agent Output Verifier by SarnAI sarnai-dev/agent-output-verifier Independent schema and rule check of AI agent output before you pay. Signed attestation and receipt. | |
| Memoire sarveshsea/m-moire Shadcn-native Design CI for Tailwind apps with registry export and MCP UI tools. | |
| CallFlow AI sarvin-tech/callflow-ai Paid sales-call scoring and CRM next-step analysis for AI agents. | |
| ClausePilot sarvin-tech/clausepilot x402 contract tools and premium portfolio scans for AI agents on Base. | |
| LeadForm AI sarvin-tech/leadform-ai Paid B2B lead scoring and next-action qualification for AI agents. | |
| TMTB Marketing AI Platform sasha859/tmtb-platform AI marketing skills for e-commerce brands: reports, campaign management, and creative generation. | |
| ToolSocket satashili/toolsocket 660+ data tools for agents: TikTok, Douyin, Instagram, YouTube, X, weather, GitHub. Pay per call. | |
| SatGate – Economic Firewall for AI Agents satgate-io/satgate Budget, payment and audit controls for AI agent API calls and MCP tool calls. | |
| io.github.sathergate/flagpost sathergate/sathergate-toolkit Feature flags for Next.js. One file, full control with A/B testing. | |
| Sato Hub: Build Onchain & Crypto Agents satohubai/onchain-agents Build any crypto agent: x402, ERC-8004, wallets. Does a server take your key? Hosted? Maintained? | |
| Sato Kit satohubai/sato-hub-integrations Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log. | |
| SatoshiAPI — Bitcoin Intelligence via Lightning satoshiapi/satoshi-btc-api Bitcoin intelligence API. Pay per call via L402 Lightning (10-200 sats). No accounts needed. | |
| kiriya satpaingoo/kiriya Developer tools for files, git, ports, processes and more, the same on Windows, Linux and macOS | |
| io.github.sattyamjjain/whycant sattyamjjain/whycantwehaveanagentforthis Roast any AI agent idea from your IDE: verdict tier, readiness score, top risk, shareable URL. | |
| io.github.sauliusbeconis/axongate sauliusbeconis/axongate Safe web read, search, cited answers, fact-checks and token checks for agents, paid via x402. | |
| MCP Security Sanitizer saurabhdrh/mcp-security-sanitizer Redacts common secrets, email addresses, and phone numbers. | |
| 竞品内容 Pattern 雷达 · AI 答案里的重复说法 savantcat/pattern-radar 把 AI 答案/竞品内容当语料，找出反复出现的说法、被反复引用的信源与答案同质化程度，含对照组自检 | |
| SaveWell savewell/consumer-interface Original Medicare: surgery-center vs. hospital costs, Medigap rewards, and specialists near a ZIP. | |
| SAVORDISH savordish/savor-dish AI-powered recipe platform: 18 MCP tools for meal planning, grocery lists & Instacart. | |
| com.docimprint/api sawftware-apps/darkroom-gw AI document intelligence: extract, summarize, claim-check, notarize, and signed action receipts. | |
| io.github.saxenakapil/setup-doctor saxenakapil/setup-doctor Score and improve your AI coding agent setup. Local-only, open source. | |
| Fintalio LinkedIn MCP saybil-lab/mnareach LinkedIn outreach MCP server — 19 tools for AI agents to prospect, sequence, and manage contacts. | |
| Say It Again sayitagainai/mcp AI UGC videos of your store's products: read a product, write 3 scripts, make the video. | |
| Agent Bazaar saylorinnovations/open-x402-bazaar Open, permissionless discovery marketplace for x402-payable resources. No account or KYC required. |
48,501–48,550 of 50,909
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.